Multi-View Independent Component Analysis with Shared and Individual Sources

TL;DR

This paper introduces a novel multi-view ICA method that identifies shared and individual sources from noisy observations across different views, with proven identifiability and practical applications in transcriptomics.

Contribution

The work provides theoretical guarantees for identifiability in multi-view noisy ICA and proposes a practical estimation and model selection procedure.

Findings

The model is identifiable under certain conditions.

The method accurately recovers sources in noisy settings.

Application to transcriptome data reveals meaningful shared sources.

Abstract

Independent component analysis (ICA) is a blind source separation method for linear disentanglement of independent latent sources from observed data. We investigate the special setting of noisy linear ICA where the observations are split among different views, each receiving a mixture of shared and individual sources. We prove that the corresponding linear structure is identifiable, and the source distribution can be recovered. To computationally estimate the sources, we optimize a constrained form of the joint log-likelihood of the observed data among all views. We also show empirically that our objective recovers the sources also in the case when the measurements are corrupted by noise. Furthermore, we propose a model selection procedure for recovering the number of shared sources which we verify empirically. Finally, we apply the proposed model in a challenging real-life application, where the estimated shared sources from two large transcriptome datasets (observed data) provided by two different labs (two different views) lead to recovering (shared) sources utilized for finding a plausible representation of the underlying graph structure.